Abstract
The topology-preservation characteristics of a self-organising system are studied in this paper. The system consists of a logical neural network with a structure based on the discriminator network and a method of training that presents certain similarities to Kohonen’s self-organising maps. In particular, the optimal neighbourhood size for the most accurate preservation of topological relationships is investigated. Experimental results presented in this paper indicate optimal ranges of values for some of the system’s parameters.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Aleksander, I. & Morion, H. (1990) An Introduction To Neural Computing. Chapman and Hall, England.
Kohonen, T. (1989) Self-Organisation and Associative Memory (3rd edition). Springer-Verlag, Heidelberg.
Kangas, J.A., Kohonen, T., & Laaksonen, J.T. (1991) Variants of Self-Organising Maps. IEEE Transactions on Neural Networks, Vol. 1, No. 1, pp. 93–99.
Tambouratzis, G. & Stonham, T.J. (1992a) A Logical Neural Network that Adapts to Changes in the Pattern Environment Proceedings of the II th IAPR International Conference on Pattern Recognition, The Hague, Netherlands, August 1992, Vol. 2, pp. 46–49.
Tambouratzis, G. & Stonham, T.J. (1992b) Implementing Hard Self-Organisation Tasks Using Logical Neural Networks. In Aleksander, I., & Taylor, J. (eds.) Artificial Neural Networks-2, Vol. 1, pp. 643–646. North-Holland, Amsterdam.
Tambouratzis, G. & Stonham, T.J. (1992c) Evaluating the Topology-Preservation Capabilities of a Self-Organising Logical Neural Network. Pattern Recognition Letters (in print).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag London Limited
About this paper
Cite this paper
Tambouratzis, G., Stonham, T.J. (1993). Optimal Topology-Preservation Using Self-Organising Logical Neural Networks. In: Gielen, S., Kappen, B. (eds) ICANN ’93. ICANN 1993. Springer, London. https://doi.org/10.1007/978-1-4471-2063-6_16
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2063-6_16
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-19839-0
Online ISBN: 978-1-4471-2063-6
eBook Packages: Springer Book Archive